Paper Citation Record · LEDGER

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds

As of 23 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2608.02636.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.02636 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T04:26:29.391821Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact9
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8a90af47-2e13-4c3e-8349-8cdfb7b7574f · outbound

This paper cites EvoSkill: Automated Skill Discovery for Multi-Agent Systems.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds EvoSkill: Automated Skill Discovery for Multi-Agent Systems

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.265105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18af5fd2-88ac-4fc7-ac73-bc12688d9576 · outbound

This paper cites SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:30.139623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9d048cba-0f7a-4671-b27c-07acf4501c60 · outbound

This paper cites SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.271710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d573934b-8996-49a3-8944-c0c4d767976c · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.274719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb3ab3d6-243f-413d-bf1b-e796b3187d14 · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.277623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da706142-8e73-4fc4-b8ad-11237251da7f · outbound

This paper cites From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.280417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acfbd300-b814-40cd-9d04-af9322c6bef2 · outbound

This paper cites XSkill: Continual Learning from Experience and Skills in Multimodal Agents.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds XSkill: Continual Learning from Experience and Skills in Multimodal Agents

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.283638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fed06f9-0529-4d2f-9cd8-3020561fa34e · outbound

This paper cites SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.286560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58fa20bc-c295-410a-95bb-16fea1521df0 · outbound

This paper cites Scaling Test-Time Compute for Agentic Coding.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Scaling Test-Time Compute for Agentic Coding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.290506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95f65630-69b8-4636-9ef2-161050a35c54 · outbound

This paper cites SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.293299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92058c4b-c445-4dd2-ad0e-4e6966c1c73f · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.296196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55f63154-3950-4b49-bbe8-49d5060e69a2 · outbound

This paper cites SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.892330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bad87620-2186-4296-ad96-3cf3f03b1deb · outbound

This paper cites SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.301648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e54a41-474e-4ff5-9e75-47f8be8f2c9f · outbound

This paper cites SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.304596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 699cc08b-dcdc-44c5-90f5-e910149fa12c · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:26:30.187211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e615110e-6347-4862-816e-e65681dd5530 · outbound

This paper cites How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.310262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec9c1be9-b1e6-4643-b2db-647e18827e36 · outbound

This paper cites OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.858464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 83b1e150-c507-487e-bffa-8acb8ae2a665 · outbound

This paper cites SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.316067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 747e157f-1913-40c6-95f9-a1570261959f · outbound

This paper cites SkillGen: Verified Inference-Time Agent Skill Synthesis.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillGen: Verified Inference-Time Agent Skill Synthesis

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.318909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3dd4aec-278f-4817-8bb2-bb5adcc88527 · outbound

This paper cites SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.321915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d129ac94-b538-4ea4-b655-27c8cecd55c1 · outbound

This paper cites DocVQA: A Dataset for VQA on Document Images.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds DocVQA: A Dataset for VQA on Document Images

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.325114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37b73046-1654-4079-b455-f186f90fa14e · outbound

This paper cites Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.327977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ab4ef07-982a-40c0-86e7-a8821620c382 · outbound

This paper cites SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.809426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 444b5b2f-57e0-4342-8fcc-f74e664e65a6 · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.334462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18c3dbf0-38eb-4ba7-ba9b-2fa95d16a092 · outbound

This paper cites R.; and He, J.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds R.; and He, J

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.337210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d04dce0-a820-4887-a171-71257e024395 · outbound

This paper cites Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.339844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02a96305-95c2-4c11-ab65-4db24ccec6ee · outbound

This paper cites Rethinking the Evaluation of Harness Evolution for Agents.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Rethinking the Evaluation of Harness Evolution for Agents

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.711759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7a2f5bd7-bbc5-42b7-b697-481fa4ff587a · outbound

This paper cites SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.345332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96c076d9-fccb-4c1f-8331-65a1b01d75da · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:26:30.179098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8addd9b3-4fe9-4190-b425-743bc2f9a061 · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:26:30.171556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b8a5a7d7-7938-4c98-a4ca-d13e1c76c8ca · outbound

This paper cites Skill-Conditioned Visual Geolocation for Vision-Language Models.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Skill-Conditioned Visual Geolocation for Vision-Language Models

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.691085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a86c4f3d-e13a-4cc3-b0d9-7ef0787533a8 · outbound

This paper cites OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.679897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 81faf9b9-3db9-42d6-b7ec-5deb09505f9e · outbound

This paper cites SkillOpt: Executive Strategy for Self-Evolving Agent Skills.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.358801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5854a29-09ce-4017-bbf6-9560a24e1fb1 · outbound

This paper cites SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.361478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5883115-6951-4dbe-85eb-0ef540f5b813 · outbound

This paper cites CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.364049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68158858-c01c-445b-b13e-187b67e05b4f · outbound

This paper cites MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.366925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e3457d-8e86-4fcf-9e40-79dffe3fd814 · outbound

This paper cites Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.626275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e1d9a413-c87a-429a-9146-fd27b8c96466 · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:26:30.163633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 110a6aeb-ba03-4cb8-aa2e-16f4f1f6f660 · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:26:30.156009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dbfa9deb-3eb3-4d92-8206-3c9559c6a196 · outbound

This paper cites an unresolved cited work.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.377768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d7abf58-df95-434f-8ac0-5523cb524756 · outbound

This paper cites SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.380459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bfd5ccd-2d30-45b6-a10b-c7fbd796f103 · outbound

This paper cites SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.383456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f885bcb-efb6-476d-ae95-48019eceee17 · outbound

This paper cites Counterfactual Trace Auditing of LLM Agent Skills.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Counterfactual Trace Auditing of LLM Agent Skills

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.386449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1dd6a32-e818-46c8-b774-832296dca72a · outbound

This paper cites SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:26:29.435016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ddbf3e45-f320-4df8-b7ba-3f42e3441114 · outbound

This paper cites Scaling Test-time Compute for LLM Agents.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Scaling Test-time Compute for LLM Agents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.391821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.